© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 83795
    Prev
    Next
    INDEX
    Explanations

    references to time-sensitive events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ttl
    -0.07
    .idea
    -0.07
    kv
    -0.07
    wang
    -0.06
    auer
    -0.06
    ropolitan
    -0.06
    ĥ
    -0.06
    OLOR
    -0.06
    META
    -0.06
    achs
    -0.06
    POSITIVE LOGITS
     Rocket
    0.07
    Rocket
    0.07
     ÑģÑĥÑĤ
    0.06
     rocket
    0.06
     Mission
    0.06
    Cube
    0.06
    rocket
    0.06
     Vz
    0.06
    ockets
    0.06
    ëĭ´
    0.06
    Activations Density 0.001%

    No Known Activations